| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2434, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.0993, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 2.1794, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.1871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.1112499237060547, | |
| "eval_runtime": 6.1153, | |
| "eval_samples_per_second": 3.27, | |
| "eval_steps_per_second": 3.27, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 1434058374512640.0, | |
| "train_loss": 2.172952950000763, | |
| "train_runtime": 88.3266, | |
| "train_samples_per_second": 0.226, | |
| "train_steps_per_second": 0.226 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "total_flos": 1434058374512640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |